Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    277
    -0.07
     barren
    -0.07
    FIT
    -0.07
    ury
    -0.07
    liers
    -0.06
     SVM
    -0.06
    シ
    -0.06
    aný
    -0.06
    iore
    -0.06
    When
    -0.06
    POSITIVE LOGITS
    ateau
    0.07
     adjusting
    0.07
     enhancements
    0.06
     setUsername
    0.06
     seleccion
    0.06
     scrolled
    0.06
    >')↵
    0.06
     prz
    0.06
    _experiment
    0.06
     Desert
    0.06
    Act Density 0.033%

    No Known Activations